TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Zexi, Xie, Tao, Xiao, Haoyi, Yang, Baoyao, Ji, Yuzhu, Zeng, An, Zhang, Xiang, Zhang, Yiqun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914248224931840
author Tan, Zexi
Xie, Tao
Xiao, Haoyi
Yang, Baoyao
Ji, Yuzhu
Zeng, An
Zhang, Xiang
Zhang, Yiqun
author_facet Tan, Zexi
Xie, Tao
Xiao, Haoyi
Yang, Baoyao
Ji, Yuzhu
Zeng, An
Zhang, Xiang
Zhang, Yiqun
contents Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning (CL), are prominent for MTS representation, existing CL-based models face two key limitations: 1) neglecting clustering information during positive/negative sample pair construction, and 2) introducing unreasonable inductive biases, e.g., destroying time dependence and periodicity through augmentation strategies, compromising representation quality. This paper, therefore, proposes a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework. To preserve temporal structure while generating low-distortion representations, a temporal-frequency Co-EnHancement (CoEH) mechanism is introduced. Accordingly, a synergistic dual-path representation and cluster distribution learning framework is designed to jointly optimize cluster structure and representation fidelity. Experiments on six real-world benchmark datasets demonstrate TFEC's superiority, achieving 4.48% average NMI gains over SOTA methods, with ablation studies validating the design. The code of the paper is available at: https://github.com/yueliangy/TFEC.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07550
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
Tan, Zexi
Xie, Tao
Xiao, Haoyi
Yang, Baoyao
Ji, Yuzhu
Zeng, An
Zhang, Xiang
Zhang, Yiqun
Machine Learning
Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning (CL), are prominent for MTS representation, existing CL-based models face two key limitations: 1) neglecting clustering information during positive/negative sample pair construction, and 2) introducing unreasonable inductive biases, e.g., destroying time dependence and periodicity through augmentation strategies, compromising representation quality. This paper, therefore, proposes a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework. To preserve temporal structure while generating low-distortion representations, a temporal-frequency Co-EnHancement (CoEH) mechanism is introduced. Accordingly, a synergistic dual-path representation and cluster distribution learning framework is designed to jointly optimize cluster structure and representation fidelity. Experiments on six real-world benchmark datasets demonstrate TFEC's superiority, achieving 4.48% average NMI gains over SOTA methods, with ablation studies validating the design. The code of the paper is available at: https://github.com/yueliangy/TFEC.
title TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
topic Machine Learning
url https://arxiv.org/abs/2601.07550